summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2014-12-10 12:10:24 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2014-12-10 12:10:24 -0800
commitb6444bd0a18eb47343e16749ce80a6ebd521f124 (patch)
tree989881a237552dbe3fb36df45b4eda6dbd5fc09f
parent9d0cf6f56454c8a71e0aa2c3b9c6cbe470eb2788 (diff)
parent97b67ae559947f1e208439a1bf6a734da3087006 (diff)
Merge branch 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 boot and percpu updates from Ingo Molnar: "This tree contains a bootable images documentation update plus three slightly misplaced x86/asm percpu changes/optimizations" * 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86-64: Use RIP-relative addressing for most per-CPU accesses x86-64: Handle PC-relative relocations on per-CPU data x86: Convert a few more per-CPU items to read-mostly ones x86, boot: Document intermediates more clearly
-rw-r--r--arch/x86/boot/compressed/Makefile12
-rw-r--r--arch/x86/boot/compressed/misc.c14
-rw-r--r--arch/x86/include/asm/percpu.h61
-rw-r--r--arch/x86/include/asm/processor.h4
-rw-r--r--arch/x86/kernel/setup_percpu.c2
-rw-r--r--arch/x86/kernel/smpboot.c2
-rw-r--r--arch/x86/kernel/vmlinux.lds.S2
-rw-r--r--arch/x86/tools/relocs.c36
8 files changed, 103 insertions, 30 deletions
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 45abc363dd3e..65516ab0cabe 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -3,6 +3,18 @@
#
# create a compressed vmlinux image from the original vmlinux
#
+# vmlinuz is:
+# decompression code (*.o)
+# asm globals (piggy.S), including:
+# vmlinux.bin.(gz|bz2|lzma|...)
+#
+# vmlinux.bin is:
+# vmlinux stripped of debugging and comments
+# vmlinux.bin.all is:
+# vmlinux.bin + vmlinux.relocs
+# vmlinux.bin.(gz|bz2|lzma|...) is:
+# (see scripts/Makefile.lib size_append)
+# compressed vmlinux.bin.all + u32 size of vmlinux.bin.all
targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 30dd59a9f0b4..dcc1c536cc21 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -260,7 +260,7 @@ static void handle_relocations(void *output, unsigned long output_len)
/*
* Process relocations: 32 bit relocations first then 64 bit after.
- * Two sets of binary relocations are added to the end of the kernel
+ * Three sets of binary relocations are added to the end of the kernel
* before compression. Each relocation table entry is the kernel
* address of the location which needs to be updated stored as a
* 32-bit value which is sign extended to 64 bits.
@@ -270,6 +270,8 @@ static void handle_relocations(void *output, unsigned long output_len)
* kernel bits...
* 0 - zero terminator for 64 bit relocations
* 64 bit relocation repeated
+ * 0 - zero terminator for inverse 32 bit relocations
+ * 32 bit inverse relocation repeated
* 0 - zero terminator for 32 bit relocations
* 32 bit relocation repeated
*
@@ -286,6 +288,16 @@ static void handle_relocations(void *output, unsigned long output_len)
*(uint32_t *)ptr += delta;
}
#ifdef CONFIG_X86_64
+ while (*--reloc) {
+ long extended = *reloc;
+ extended += map;
+
+ ptr = (unsigned long)extended;
+ if (ptr < min_addr || ptr > max_addr)
+ error("inverse 32-bit relocation outside of kernel!\n");
+
+ *(int32_t *)ptr -= delta;
+ }
for (reloc--; *reloc; reloc--) {
long extended = *reloc;
extended += map;
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index fd472181a1d0..e0ba66ca68c6 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -64,7 +64,7 @@
#define __percpu_prefix ""
#endif
-#define __percpu_arg(x) __percpu_prefix "%P" #x
+#define __percpu_arg(x) __percpu_prefix "%" #x
/*
* Initialized pointers to per-cpu variables needed for the boot
@@ -179,29 +179,58 @@ do { \
} \
} while (0)
-#define percpu_from_op(op, var, constraint) \
+#define percpu_from_op(op, var) \
({ \
typeof(var) pfo_ret__; \
switch (sizeof(var)) { \
case 1: \
asm(op "b "__percpu_arg(1)",%0" \
: "=q" (pfo_ret__) \
- : constraint); \
+ : "m" (var)); \
break; \
case 2: \
asm(op "w "__percpu_arg(1)",%0" \
: "=r" (pfo_ret__) \
- : constraint); \
+ : "m" (var)); \
break; \
case 4: \
asm(op "l "__percpu_arg(1)",%0" \
: "=r" (pfo_ret__) \
- : constraint); \
+ : "m" (var)); \
break; \
case 8: \
asm(op "q "__percpu_arg(1)",%0" \
: "=r" (pfo_ret__) \
- : constraint); \
+ : "m" (var)); \
+ break; \
+ default: __bad_percpu_size(); \
+ } \
+ pfo_ret__; \
+})
+
+#define percpu_stable_op(op, var) \
+({ \
+ typeof(var) pfo_ret__; \
+ switch (sizeof(var)) { \
+ case 1: \
+ asm(op "b "__percpu_arg(P1)",%0" \
+ : "=q" (pfo_ret__) \
+ : "p" (&(var))); \
+ break; \
+ case 2: \
+ asm(op "w "__percpu_arg(P1)",%0" \
+ : "=r" (pfo_ret__) \
+ : "p" (&(var))); \
+ break; \
+ case 4: \
+ asm(op "l "__percpu_arg(P1)",%0" \
+ : "=r" (pfo_ret__) \
+ : "p" (&(var))); \
+ break; \
+ case 8: \
+ asm(op "q "__percpu_arg(P1)",%0" \
+ : "=r" (pfo_ret__) \
+ : "p" (&(var))); \
break; \
default: __bad_percpu_size(); \
} \
@@ -359,11 +388,11 @@ do { \
* per-thread variables implemented as per-cpu variables and thus
* stable for the duration of the respective task.
*/
-#define this_cpu_read_stable(var) percpu_from_op("mov", var, "p" (&(var)))
+#define this_cpu_read_stable(var) percpu_stable_op("mov", var)
-#define raw_cpu_read_1(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
-#define raw_cpu_read_2(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
-#define raw_cpu_read_4(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
+#define raw_cpu_read_1(pcp) percpu_from_op("mov", pcp)
+#define raw_cpu_read_2(pcp) percpu_from_op("mov", pcp)
+#define raw_cpu_read_4(pcp) percpu_from_op("mov", pcp)
#define raw_cpu_write_1(pcp, val) percpu_to_op("mov", (pcp), val)
#define raw_cpu_write_2(pcp, val) percpu_to_op("mov", (pcp), val)
@@ -381,9 +410,9 @@ do { \
#define raw_cpu_xchg_2(pcp, val) percpu_xchg_op(pcp, val)
#define raw_cpu_xchg_4(pcp, val) percpu_xchg_op(pcp, val)
-#define this_cpu_read_1(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
-#define this_cpu_read_2(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
-#define this_cpu_read_4(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_read_1(pcp) percpu_from_op("mov", pcp)
+#define this_cpu_read_2(pcp) percpu_from_op("mov", pcp)
+#define this_cpu_read_4(pcp) percpu_from_op("mov", pcp)
#define this_cpu_write_1(pcp, val) percpu_to_op("mov", (pcp), val)
#define this_cpu_write_2(pcp, val) percpu_to_op("mov", (pcp), val)
#define this_cpu_write_4(pcp, val) percpu_to_op("mov", (pcp), val)
@@ -435,7 +464,7 @@ do { \
* 32 bit must fall back to generic operations.
*/
#ifdef CONFIG_X86_64
-#define raw_cpu_read_8(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
+#define raw_cpu_read_8(pcp) percpu_from_op("mov", pcp)
#define raw_cpu_write_8(pcp, val) percpu_to_op("mov", (pcp), val)
#define raw_cpu_add_8(pcp, val) percpu_add_op((pcp), val)
#define raw_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val)
@@ -444,7 +473,7 @@ do { \
#define raw_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval)
#define raw_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval)
-#define this_cpu_read_8(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_read_8(pcp) percpu_from_op("mov", pcp)
#define this_cpu_write_8(pcp, val) percpu_to_op("mov", (pcp), val)
#define this_cpu_add_8(pcp, val) percpu_add_op((pcp), val)
#define this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val)
@@ -522,7 +551,7 @@ static inline int x86_this_cpu_variable_test_bit(int nr,
#include <asm-generic/percpu.h>
/* We can use this directly for local CPU (faster). */
-DECLARE_PER_CPU(unsigned long, this_cpu_off);
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off);
#endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 9617a1716813..25b8de0f21c0 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -127,7 +127,7 @@ struct cpuinfo_x86 {
/* Index into per_cpu list: */
u16 cpu_index;
u32 microcode;
-} __attribute__((__aligned__(SMP_CACHE_BYTES)));
+};
#define X86_VENDOR_INTEL 0
#define X86_VENDOR_CYRIX 1
@@ -151,7 +151,7 @@ extern __u32 cpu_caps_cleared[NCAPINTS];
extern __u32 cpu_caps_set[NCAPINTS];
#ifdef CONFIG_SMP
-DECLARE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
+DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
#define cpu_data(cpu) per_cpu(cpu_info, cpu)
#else
#define cpu_info boot_cpu_data
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 5cdff0357746..e4fcb87ba7a6 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -30,7 +30,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_number);
#define BOOT_PERCPU_OFFSET 0
#endif
-DEFINE_PER_CPU(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
EXPORT_PER_CPU_SYMBOL(this_cpu_off);
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = {
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 668d8f2a8781..7a8f5845e8eb 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -99,7 +99,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_core_map);
DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
/* Per CPU bogomips and other parameters */
-DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
+DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
EXPORT_PER_CPU_SYMBOL(cpu_info);
atomic_t init_deasserted;
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 49edf2dd3613..00bf300fd846 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -186,6 +186,8 @@ SECTIONS
* start another segment - init.
*/
PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu)
+ ASSERT(SIZEOF(.data..percpu) < CONFIG_PHYSICAL_START,
+ "per-CPU data too large - increase CONFIG_PHYSICAL_START")
#endif
INIT_TEXT_SECTION(PAGE_SIZE)
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index a5efb21d5228..0c2fae8d929d 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -20,7 +20,10 @@ struct relocs {
static struct relocs relocs16;
static struct relocs relocs32;
+#if ELF_BITS == 64
+static struct relocs relocs32neg;
static struct relocs relocs64;
+#endif
struct section {
Elf_Shdr shdr;
@@ -762,11 +765,16 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
switch (r_type) {
case R_X86_64_NONE:
+ /* NONE can be ignored. */
+ break;
+
case R_X86_64_PC32:
/*
- * NONE can be ignored and PC relative relocations don't
- * need to be adjusted.
+ * PC relative relocations don't need to be adjusted unless
+ * referencing a percpu symbol.
*/
+ if (is_percpu_sym(sym, symname))
+ add_reloc(&relocs32neg, offset);
break;
case R_X86_64_32:
@@ -986,7 +994,10 @@ static void emit_relocs(int as_text, int use_real_mode)
/* Order the relocations for more efficient processing */
sort_relocs(&relocs16);
sort_relocs(&relocs32);
+#if ELF_BITS == 64
+ sort_relocs(&relocs32neg);
sort_relocs(&relocs64);
+#endif
/* Print the relocations */
if (as_text) {
@@ -1007,14 +1018,21 @@ static void emit_relocs(int as_text, int use_real_mode)
for (i = 0; i < relocs32.count; i++)
write_reloc(relocs32.offset[i], stdout);
} else {
- if (ELF_BITS == 64) {
- /* Print a stop */
- write_reloc(0, stdout);
+#if ELF_BITS == 64
+ /* Print a stop */
+ write_reloc(0, stdout);
- /* Now print each relocation */
- for (i = 0; i < relocs64.count; i++)
- write_reloc(relocs64.offset[i], stdout);
- }
+ /* Now print each relocation */
+ for (i = 0; i < relocs64.count; i++)
+ write_reloc(relocs64.offset[i], stdout);
+
+ /* Print a stop */
+ write_reloc(0, stdout);
+
+ /* Now print each inverse 32-bit relocation */
+ for (i = 0; i < relocs32neg.count; i++)
+ write_reloc(relocs32neg.offset[i], stdout);
+#endif
/* Print a stop */
write_reloc(0, stdout);